Skip to main content

Über dieses Buch

This book constitutes the refereed proceedings of the International Conference for Smart Health, ICSH 2013, held in Beijing, China, in August 2013. The 15 revised full papers presented were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on Information Sharing, Integrating and Extraction; Mining Clinical and Medical Data; Smart Health Applications.



Information Sharing, Integrating and Extraction

Portrayal of Electronic Cigarettes on YouTube

Despite the growing number of videos featuring electronic cigarettes, there has been no investigation of the portrayal of these videos. This paper presents the first surveillance data of electronic cigarette videos on YouTube. Our results suggest that viewers are primarily being exposed to content promoting the use of these emerging tobacco products and the viewership is global. This study shows that it is critical to develop appropriate health campaigns to inform potential consumers of harms associated with electronic cigarette use.

Chuan Luo, Xiaolong Zheng, Daniel Dajun Zeng, Scott Leischow, Kainan Cui, Zhu Zhang, Saike He

The Effectiveness of Smoking Cessation Intervention on Facebook: A Preliminary Study of Posts and Users

Smoking causes many serious illnesses such as lung cancer, chronic bronchitis, and emphysem. Some intervention programs of smoking cessation are developed online, which can reach a large number of people at any time. QuitNet is one of the most popular websites of smoking cessation. It developed a public page on Facebook, providing information and initiating discussions on smoking cessation. In this study, we explore the features of QuitNet Facebook through preliminary qualitative and quantitative analysis. We collect data of posts and comments from 04/01/2011 to 06/31/2011on QuitNet Facebook and analyze the data from the post and user perspectives. For the post perspective, we analyze popular posts which receive the most and the soonest comments from Facebook users, and find that most of these posts ask for responses of user motivations, methods, experiences and emotions of smoking abstinence. For the user perspective, we analyze users who make comments more frequently and immediately after a post being published, and find that users at the maintenance stage of smoking cessation are more active than those at the early actions stage.

Mi Zhang, Christopher C. Yang

An Empirical Analysis of Social Interaction on Tobacco-Oriented Social Networks

Social media is widely utilized in the tobacco control campaigns. It is a great challenge to evaluate the efficiency of tobacco control policies on social network sites and find gaps among tobacco-oriented social networks. In this paper, we construct three tobacco-oriented social networks according to user interaction on Facebook tobacco-related fan pages. We further investigate the interaction patterns including temporal distribution and interaction patterns to reveal the differences of tobacco-oriented social networks. Our empirical analysis demonstrates that: 1) the user interaction on the pro-tobacco fan pages is more active. Fan pages for tobacco promotion are more successful in obtaining more user attention. 2) The gap between tobacco promotion and tobacco control is widening. These empirical results can provide us significant insights into understanding the evolutionary patterns of social interaction in tobacco-oriented social networks and further help the government departments of tobacco control to make reasonable decisions.

Yunji Liang, Xiaolong Zheng, Daniel Dajun Zeng, Xingshe Zhou, Scott Leischow

An Analysis of Beijing HFMD Patients Mobility Pattern during Seeking Treatment

Previous epidemiological researches have studied HFMD transmission pattern, but the study on the patients mobility pattern while seeking treatment is absent. In this paper, we present a statistical analysis of the spatialtemporal pattern of the Beijing HFMD patients mobility based on a complete works dataset containing over 40,000 cases in 2010. The main findings are as follows: (1) the patents incline to take their sick children to hospitals on weekdays, especially on Monday; (2) the patients living far from city center are more likely to get to hospitals in the afternoon, while the patients in the downtown in the morning; (3) patients (or their parents) either select the nearby hospitals, or the Class-A hospitals in the downtown. Furthermore, we employ a gravity model to describe the spatial mobility pattern of patients. The experiment results show a good fit.

Zhaonan Zhu, Zhidong Cao, Daniel Dajun Zeng

Mining Clinical and Medical Data

Phenotyping on EHR Data Using OWL and Semantic Web Technologies


In this paper, we introduce our efforts on using semantic web technologies to execute phenotyping algorithms on Electronic Health Records (EHR) data.

Cui Tao, Dingcheng Li, Feichen Shen, Zonghui Lian, Jyotishman Pathak, Hongfang Liu, Christopher G. Chute

Spatial, Temporal, and Space-Time Clusters of Hemorrhagic Fever with Renal Syndrome in Beijing, China

As only few cases each year, the distribution of hemorrhagic fever with renal syndrome (HFRS) had thought to be sporadic using the traditional statistical method. The cases reported between 2007 and 2012 through notifiable disease system were analyzed using SaTScan software. The spatial, temporal and space-time distribution of HFRS cases and clusters of high risk at township level was explored. The clusters in northern remote suburb, south of central urban and northern urban fringe were identified. When clusters were found, we could find evidence of risk factors easily and provide proper prevention methods ultimately. The cluster methods may have wider applications in the diseases with few cases.

Xiangfeng Dou, Yi Jiang, Changying Lin, Lili Tian, Xiaoli Wang, Kaikun Qian, Xiuchun Zhang, Xinyu Li, Yanning Lyu, Yulan Sun, Zengzhi Guan, Shuang Li, Quanyi Wang

Extracting and Normalizing Temporal Expressions in Clinical Data Requests from Researchers

Automatic translation of clinical researcher data requests to executable database queries is instrumental to an effective interface between clinical researchers and “Big Clinical Data”. A necessary step towards this goal is to parse ample temporal expressions in free-text researcher requests. This paper reports a novel algorithm called TEXer. It uses heuristic rule and pattern learning for extracting and normalizing temporal expressions in researcher requests. Based on 400 real clinical queries with human annotations, we compared our method with four baseline methods. TEXer achieved a precision of 0.945 and a recall of 0.858, outperforming all the baseline methods. We conclude that TEXer is an effective method for temporal expression extraction from free-text clinical data requests.

Tianyong Hao, Alex Rusanov, Chunhua Weng

Exploring Interoperability Approaches and Challenges in Healthcare Data Exchange

Today e-health data and its usage in various dimensions is one of the most discussed issues. The nature of health data is heterogeneous and distributed, accessed through varied formats and architectures supporting different vocabularies. Interoperable electronic Health Record (EHR) systems are the most important enabling tools on the road to patient-centric care, a lifeline for continuity of care and support to mobility of patients. Also, hospitals refer cases to other hospitals located in same or different cities or countries altogether leading to sharing of information. This generates the reason to study the suitability of available models and protocols enabling exchange of sensitive and time critical health information during open-ended transmission. The issue of sharing data in integrated applications is highly significant and affected by various implicit and explicit factors in terms of technologies and adoption by health providers. Varied architectural approaches are implemented by vendors for designing a HIS (Hospital Information System) without giving any consideration to integrated and interoperable sharing of data. Such disparate systems are best when used in isolation but very weak when try to talk with each other. This paper aims to review issues related creation of architectures in the perspective of sharing of electronic health records and the challenges faced by them in an interoperable environment.

Shalini Bhartiya, Deepti Mehrotra

Visual Data Discovery to Support Patient Care

Adopting electronic health records fuel exponential data growth. However, more data doesn’t necessarily lead to more information unless you have an efficient tool to translate massive data into actionable insights in real time and in a cost-effective manner. This paper is a preliminary study which introduces a new breed of data discovery technology and its value as emerging differentiator from traditional business intelligence, especially in the usability perspective. We present an exemplary case of using QlikView for clinical report dashboard. Physicians and care providers explore patient populations, data patterns, answer questions spontaneously, and forge new drill paths through data volume of millions of rows. Initial evaluation result is promising and indicates visual data discovery tool empowers end users with intuitive and interactive experience, rapid deployment, customizable ad-hoc questions and answers. The next step will be integration with data governance, advanced statistics, predictive modeling and thorough user evaluation with subject matter experts including clinical and IT staff.

Jihong Zeng, John Zhang

Smart Health Applications

DiabeticLink: A Health Big Data System for Patient Empowerment and Personalized Healthcare

Ever increasing rates of diabetes and healthcare costs have focused our attention on this chronic disease to provide a health social media system to serve multi-national markets. Our


system has been developed in both the US and Taiwan markets, addressing the needs of patients, caretakers, nurse educators, physicians, pharmaceutical company and researchers alike to provide features that encourage social connection, data sharing and assimilation and educational opportunities. Some important features


offers include diabetic health indicator tracking, electronic health record (EHR) search, social discussion and Q&A forums, health information resources, diabetic medication side effect reporting, healthy eating recipes and restaurant recommendations. We utilize advanced data, text and web mining algorithms and other computational techniques that are relevant to healthcare decision support and cyber-enabled patient empowerment.

Hsinchun Chen, Sherri Compton, Owen Hsiao

A Biofeedback System for Mobile Healthcare Based on Heart Rate Variability

Heart rate variability biofeedback provides a new technique for the evaluation of autonomic nervous system status and the treatment of cardiovascular diseases. This paper presents a mobile and real-time monitoring healthcare application of heart rate variability biofeedback, referred to as uCoherence. It consists of an automated approach to help people to voluntarily regular the autonomic system via breath control, finding the harmony point in autonomic nervous system and the best resonant frequency in cardiopulmonary system.

Meijun Xiong, Rui He, Lianying Ji, Jiankang Wu

Bootstrapping Activity Modeling for Ambient Assisted Living

In many societies, the age profile of the population is increasing, posing many challenges for societies, health services and carers. One response to this unfolding situation has been to direct research effort towards Ambient Assisted Living (AAL), specifically, its enabling technologies. A critical impediment to the deployment of such systems remains the accurate and timely identification of the Activities of Daily Living (ADLs). This paper advocates a minimalist approach to ADL recognition; rather than capturing all possible ADLs, the reliable identification of a select subset of ADLs may prove sufficient for many categories of AAL services. A methodology is described and initial results presented.

Jie Wan, Michael J. O’Grady, Gregory M. P. O’Hare

Healthcare Information System: A Facilitator of Primary Care for Underprivileged Elderly via Mobile Clinic

Ageing is a global challenge. As health conditions gradually deteriorate, elders are prone to suffering from multiple chronic diseases. The impact of ageing on the heath system is therefore unprecedented. Primary and preventive care is important to ensure older adults to receive immediate healthcare so that their health problems can be handled and alleviated in a timely manner, thus reducing the risk of development into serious illnesses. However, degradation of mobility in elderly becomes a hurdle to the access of healthcare services. In the paper, we present an outreach community healthcare model via a mobile clinic, which provides health assessment, interventions and health education to community-dwelling elderly. A key highlight of the mobile healthcare model is the adoption of healthcare information system (HIS) to streamline the operations and to enable smooth service delivery even with tight human resource. The role of information technology, the resulting benefits and outcomes are discussed in the paper. The HIS-leveraged mobile healthcare model is highly praised by the community and serves as an exemplar for establishing mobile clinics for various healthcare services.

Kup-Sze Choi, Rebecca K. P. Wai, Esther Y. T. Kwok

Kalico: A Smartphone Application for Health-Smart Menu Selection within a Budget

Smartphone apps are increasingly in use for personalized and preventive health and wellness management. Many preventive and manageable health conditions such as obesity, diabetes, and hypertension can be addressed through proper smartphone-based dietary interventions. Our research aims at developing a smartphone-based dietary software that helps users select a healthy eat-out menu item within a budget. To this end, our contribution in this research is three-fold: first, we identify gaps in existing smartphone apps; second, we elicit requirements for a smartphone-based dietary intervention app; third, following the elicited requirements, we design and develop an android app.

Mohd Anwar, Edward Hill, John Skujins, Kitty Huynh, Cristopher Doss

Walk Route Recommendation for Fitness Walkers Using Calorie Consumption Prediction

In this paper, we propose a novel method for recommendation of a walking route for fitness walkers, effective for health maintenance. Recently, lifestyle-related disease has been increasing in the world. It is important for people to keep balance between the calorie intake and the calorie consumption. We focus on calorie consumption by walking. Walking is effective exercise for maintaining and promoting healthy life. It is necessary to select a walking route where calorie consumption makes effectively. We propose a method of the recommendation of the walking route which can use an effective calorie in consideration of the characteristic of the user. The method is mainly composed of two features: prediction of calorie consumption and search of an appropriate walking route. Some evaluation results of our method are also described in the paper.

Yuki Sakon, Hung-Hsuan Huang, Kyoji Kawagoe

AZDrugMiner: An Information Extraction System for Mining Patient-Reported Adverse Drug Events in Online Patient Forums

Post-marketing drug surveillance is a critical component of drug safety. Drug regulatory agencies such as the U.S. Food and Drug Administration (FDA) rely on voluntary reports from health professionals and consumers contributed to its FDA Adverse Event Reporting System (FAERS) to identify adverse drug events (ADEs). However, it is widely known that FAERS underestimates the prevalence of certain adverse events. Popular patient social media sites such as DailyStrength and PatientsLikeMe provide new information sources from which patient-reported ADEs may be extracted. In this study, we propose an analytical framework for extracting patient-reported adverse drug events from online patient forums. We develop a novel approach – the AZDrugMiner system – based on statistical learning to extract ad-verse drug events in patient discussions and identify reports from patient experiences. We evaluate our system using a set of manually annotated forum posts which show promising performance. We also examine correlations and differences between patient ADE reports extracted by our system and reports from FAERS. We conclude that patient social media ADE reports can be extracted effectively using our proposed framework. Those patient reports can reflect unique perspectives in treatment and be used to improve patient care and drug safety.

Xiao Liu, Hsinchun Chen


Weitere Informationen

Premium Partner

Neuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Product Lifecycle Management im Konzernumfeld – Herausforderungen, Lösungsansätze und Handlungsempfehlungen

Für produzierende Unternehmen hat sich Product Lifecycle Management in den letzten Jahrzehnten in wachsendem Maße zu einem strategisch wichtigen Ansatz entwickelt. Forciert durch steigende Effektivitäts- und Effizienzanforderungen stellen viele Unternehmen ihre Product Lifecycle Management-Prozesse und -Informationssysteme auf den Prüfstand. Der vorliegende Beitrag beschreibt entlang eines etablierten Analyseframeworks Herausforderungen und Lösungsansätze im Product Lifecycle Management im Konzernumfeld.
Jetzt gratis downloaden!